A Deep Reinforcement Learning Approach to Audio-Based Navigation in a Multi-Speaker Environment

In this work we use deep reinforcement learning to create an autonomous agent that can navigate in a two-dimensional space using only raw auditory sensory information from the environment, a problem that has received very little attention in the reinforcement learning literature. Our experiments sho...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2021-05
Hauptverfasser:	Giannakopoulos, Petros, Pikrakis, Aggelos, Cotronis, Yannis
Format:	Artikel
Sprache:	eng
Schlagworte:	Audio equipment Auditory perception Autonomous navigation Collision avoidance Computer Science - Learning Computer Science - Sound Deep learning Target recognition
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!